Cost Tracking
affaan-m/ECC
Track and report Claude Code token usage, spending, and budgets from the local ECC cost-tracker metrics log.
Every Tesla mobile-app feature, plus a charging-cost ledger and supercharger queue watcher no other Tesla CLI ships.
$ npx skills add mvanhorn/printing-press-library --skill pp-tesla -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mvanhorn/printing-press-library pp-tesla --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cli-skills/pp-tesla .claude/skills/pp-tesla && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "pp-tesla" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-tesla into .claude/skills/pp-tesla/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-tesla", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-teslaType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mvanhorn/printing-press-library --skill pp-tesla -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mvanhorn/printing-press-library pp-tesla --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .agents/skills && cp -r skills-src/cli-skills/pp-tesla .agents/skills/pp-tesla && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "pp-tesla" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-tesla into .agents/skills/pp-tesla/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-tesla", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mvanhorn/printing-press-library --skill pp-tesla -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mvanhorn/printing-press-library pp-tesla --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/cli-skills/pp-tesla .cursor/skills/pp-tesla && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "pp-tesla" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-tesla into .cursor/skills/pp-tesla/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-tesla", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mvanhorn/printing-press-library.git --path cli-skills/pp-tesla--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mvanhorn/printing-press-library --skill pp-tesla -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mvanhorn/printing-press-library pp-tesla --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/cli-skills/pp-tesla .gemini/skills/pp-tesla && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "pp-tesla" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-tesla into .gemini/skills/pp-tesla/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-tesla", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mvanhorn/printing-press-library pp-teslaInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mvanhorn/printing-press-library --skill pp-tesla -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .github/skills && cp -r skills-src/cli-skills/pp-tesla .github/skills/pp-tesla && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "pp-tesla" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-tesla into .github/skills/pp-tesla/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-tesla", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mvanhorn/printing-press-library --skill pp-tesla -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mvanhorn/printing-press-library pp-tesla --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/cli-skills/pp-tesla .opencode/skills/pp-tesla && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "pp-tesla" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-tesla into .opencode/skills/pp-tesla/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-tesla", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
pp-teslaEvery Tesla mobile-app feature, plus a charging-cost ledger and supercharger queue watcher no other Tesla CLI ships.
Pp Tesla is an agent skill from mvanhorn/printing-press-library. Every Tesla mobile-app feature, plus a charging-cost ledger and supercharger queue watcher no other Tesla CLI ships. Trigger phrases: is my tesla ready, precondition my tesla, how much did i spend on charging this month, supercharger queue at, send this address to my tesla, list my tesla keys, use tesla, run tesla.
Its SKILL.md is about 6.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Official library of CLIs generated by the CLI Printing Press. Endorsed, tested, and community-contributed. The licence is Apache-2.0.
3 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 76de244. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadBashFrom allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
gogitvercelclaudenpxscpcargoFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
github.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Pp Tesla loads about 6.6k tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 2,424 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
allowed-tools: Read, BashAutomated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from mvanhorn/printing-press-library at commit 76de244, republished under its Apache-2.0 licence (© mvanhorn). 2,424 words, ~6,598 tokens.
.claude/skills/pp-tesla/SKILL.md (or your agent's skills folder).<!-- GENERATED FILE — DO NOT EDIT.
This file is a verbatim mirror of library/devices/tesla/SKILL.md,
regenerated post-merge by tools/generate-skills/. Hand-edits here are
silently overwritten on the next regen. Edit the library/ source instead.
See the repository agent guide, section "Generated artifacts: registry.json, cli-skills/". -->
This skill drives the tesla-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:
$HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows:npx -y @mvanhorn/printing-press-library install tesla --cli-onlytesla-pp-cli --version$PATH for the agent/runtime that will invoke this skill.If the npx install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.6 or newer):
go install github.com/mvanhorn/printing-press-library/library/devices/tesla/cmd/tesla-pp-cli@latestIf --version reports "command not found" after install, the runtime cannot see the binary directory on $PATH. Do not proceed with skill commands until verification succeeds.
Use tesla-pp-cli when you want a JSON-first CLI for your Tesla owner account: vehicle state inspection, climate/lock/charge commands, charging cost analytics, and an MCP surface for AI agents to drive your car. Faster than the iOS app for one-off commands, more agent-friendly than TeslaPy, and ships a local SQLite that delivers TeslaMate-style analytics (drives, charges, vampire drain, cost ledger) without standing up Postgres+Grafana. Best fit for owners with pre-2021 Models S/X or 3/Y on the old REST endpoints; newer vehicles get a clear shim via tesla reachability.
These capabilities aren't available in any other tool for this API.
ready — Single yes/no answer to "can I leave in 5 minutes?" with reasoned blocker list - SOC vs trip distance, plugged-in, doors closed, sentry off, cabin within 3F of target, no mid-install update
Most-asked Tesla owner question; the iOS app makes it a 6-tap diagnostic, agents need a one-call truth
tesla ready 5YJ3E1EA6XXXXXXXX --jsoncost ledger — Per-session cost, monthly spend, home-vs-Supercharger ratio with tariff-window aware $/kWh
Charging cost is the #1 Tesla-owner spreadsheet exercise; this is the first pure-CLI replacement for the TeslaMate dashboard
tesla cost ledger --since 2026-04-01 --group supercharger --jsoncost what-if — "If you had only charged at home you would have saved $X over the last 90 days." Re-runs charge rows with home $/kWh substituted for Supercharger sessions
Most Tesla owners suspect they could save by charging at home but lack proof; this puts a dollar figure on it
tesla cost what-if --only-home --since 90d --jsontimeline — Stitched drives + charges from synced vehicle_states polls - start/end, distance, energy, efficiency, address-resolved lat/lng
Lets agents reason over the same data TeslaMate exposes, without standing up Docker+Postgres+Grafana
tesla timeline --since "last week" --jsonvampire — SOC delta vs idle time, flags suspicious sentry sessions or app-wake events
Warranty-dispute evidence and rogue-sentry detection; TeslaMate dashboard only otherwise
tesla vampire --threshold 1.5pct/24h --since 30d --jsonsupercharger watch — Single-poll snapshot of free stalls at a saved Supercharger; --watch repeats every N seconds with JSON-lines transitions
Avoids the I-90 Issaquah queue at peak; pageable from an agent on a drive
tesla supercharger watch 1000 --free-stalls 2 --watch --jsonkeys audit — Lists every enrolled key with last-seen, role, form-factor; flags keys not seen >90d as stale candidates for removal
Security-minded owners worry about old phones and abandoned NFC cards still pairing with their car; this is the quarterly review
tesla keys audit --stale-after 90d --jsondoctor — Detects signed-command-required errors, classifies the vehicle as REST-friendly vs signed-command-required, prints tesla-control enrollment URL when needed
Tesla's 2024-2026 signed-command rollout is the #1 user-facing landmine for any Tesla CLI; this is the only one that surfaces it clearly
tesla doctor --jsonThis CLI was generated with browser-observed traffic context.
charging — Supercharger queue position and charging status
tesla-pp-cli charging — Current Supercharger queue position (which stall, ETA)diagnostics — Vehicle diagnostic feature config
tesla-pp-cli diagnostics — Vehicle diagnostic feature flagsenergy_sites — Powerwall and solar energy site config
tesla-pp-cli energy_sites create-set-backup-reserve — Set Powerwall backup reserve percenttesla-pp-cli energy_sites create-set-operation — Set Powerwall operation modetesla-pp-cli energy_sites get-calendar-history — Historical energy data per day/monthtesla-pp-cli energy_sites get-live-status — Real-time Powerwall solar/grid/battery powertesla-pp-cli energy_sites get-rate-tariffs — Utility rate plans for Powerwall schedulingtesla-pp-cli energy_sites get-site-info — Energy site config (capacity, type, address)tesla-pp-cli energy_sites get-site-status — Backup-reserve and operation modelogs — Client-side telemetry sink
tesla-pp-cli logs — Forward client-side log events (mostly internal use)notification_preferences — Push notification settings
tesla-pp-cli notification_preferences — Update push notification preferencesproducts — Vehicles, Powerwalls, and solar products owned by the user
tesla-pp-cli products — List vehicles, Powerwalls, and solar products ownedusers — Account config, feature flags, orders, and key/credential management
tesla-pp-cli users create-keys — Add a virtual phone key or BLE keytesla-pp-cli users get-app-config — Mobile app feature flags and runtime configtesla-pp-cli users get-feature-config — Account-level feature gatingtesla-pp-cli users get-orders — Tesla orders (new vehicle deliveries, accessory purchases)vehicles — Per-vehicle data, climate, locks, remote start, and Hermes telemetry token
tesla-pp-cli vehicles create-actuate-trunk — Open/close trunk or frunk; which_trunk = front | reartesla-pp-cli vehicles create-add-charge-schedule — Add a charging schedule (location + time window)tesla-pp-cli vehicles create-add-precondition-schedule — Add a preconditioning scheduletesla-pp-cli vehicles create-adjust-volume — Set volume to specific leveltesla-pp-cli vehicles create-auto-conditioning-start — POST /api/1/vehicles/{vehicle_id}/command/auto_conditioning_starttesla-pp-cli vehicles create-auto-conditioning-stop — POST /api/1/vehicles/{vehicle_id}/command/auto_conditioning_stoptesla-pp-cli vehicles create-bioweapon-mode — Toggle bioweapon defense mode (HEPA recirculation)tesla-pp-cli vehicles create-cancel-software-update — Cancel pending software updatetesla-pp-cli vehicles create-charge-max-range — Set charge limit to Max Range (100%)tesla-pp-cli vehicles create-charge-port-door-close — Close the charge porttesla-pp-cli vehicles create-charge-port-door-open — Open the charge porttesla-pp-cli vehicles create-charge-standard — Set charge limit to Standard (~90%)tesla-pp-cli vehicles create-charge-start — Start chargingtesla-pp-cli vehicles create-charge-stop — Stop chargingtesla-pp-cli vehicles create-climate-keeper-mode — Climate keeper mode: 0=off, 1=on, 2=dog, 3=camptesla-pp-cli vehicles create-door-lock — POST /api/1/vehicles/{vehicle_id}/command/door_locktesla-pp-cli vehicles create-door-unlock — POST /api/1/vehicles/{vehicle_id}/command/door_unlocktesla-pp-cli vehicles create-erase-user-data — Erase guest-session user datatesla-pp-cli vehicles create-flash-lights — Flash headlightstesla-pp-cli vehicles create-guest-mode — Enable/disable Guest modetesla-pp-cli vehicles create-hermes — POST /api/1/vehicles/{vehicle_id}/jwt/hermestesla-pp-cli vehicles create-honk-horn — Honk the horntesla-pp-cli vehicles create-max-defrost — Toggle max defrosttesla-pp-cli vehicles create-media-next-favorite — Next favorite stationtesla-pp-cli vehicles create-media-next-track — Next tracktesla-pp-cli vehicles create-media-prev-favorite — Previous favorite stationtesla-pp-cli vehicles create-media-prev-track — Previous tracktesla-pp-cli vehicles create-media-toggle-playback — Toggle play/pausetesla-pp-cli vehicles create-media-volume-down — Volume downtesla-pp-cli vehicles create-media-volume-up — Volume uptesla-pp-cli vehicles create-navigation-gps-request — Send lat/lng directly to navigationtesla-pp-cli vehicles create-remote-start-drive — POST /api/1/vehicles/{vehicle_id}/command/remote_start_drivetesla-pp-cli vehicles create-remove-charge-schedule — Remove charging schedule by idtesla-pp-cli vehicles create-remove-precondition-schedule — Remove preconditioning schedule by idtesla-pp-cli vehicles create-reset-valet-pin — Reset Valet PINtesla-pp-cli vehicles create-schedule-software-update — Schedule the pending software updatetesla-pp-cli vehicles create-seat-heater-request — Set seat heater level (0-3) at a seat position (0=driver, 1=passenger, 2-5=rear)tesla-pp-cli vehicles create-set-charge-limit — Set charge limit percent (50-100)tesla-pp-cli vehicles create-set-charging-amps — Set charging amps drawtesla-pp-cli vehicles create-set-sentry-mode — Enable/disable Sentry modetesla-pp-cli vehicles create-set-temps — Set driver and passenger climate temps (Celsius)tesla-pp-cli vehicles create-set-valet-mode — Enable/disable Valet mode with optional PINtesla-pp-cli vehicles create-share — Send navigation destination to the car (address or coordinates)tesla-pp-cli vehicles create-speed-limit-activate — Activate Speed Limit modetesla-pp-cli vehicles create-speed-limit-clear-pin — Clear Speed Limit PINtesla-pp-cli vehicles create-speed-limit-deactivate — Deactivate Speed Limit modetesla-pp-cli vehicles create-speed-limit-set-limit — Set Speed Limit value (mph)tesla-pp-cli vehicles create-steering-wheel-heater-request — Toggle steering wheel heatertesla-pp-cli vehicles create-sun-roof-control — Sun roof: state = vent | closetesla-pp-cli vehicles create-trigger-homelink — Trigger HomeLink garage doortesla-pp-cli vehicles create-wake-up — Wake the vehicle from sleeptesla-pp-cli vehicles create-window-control — Vent or close all windows; command = vent | closetesla-pp-cli vehicles get-compose-image — Compose a rendered image of the configured vehicletesla-pp-cli vehicles get-data-charge-state — Charge state subset (faster than full vehicle_data)tesla-pp-cli vehicles get-data-climate-state — Climate state subsettesla-pp-cli vehicles get-data-drive-state — Drive state (location, speed, shift) subsettesla-pp-cli vehicles get-data-gui-settings — GUI settings (units, time format)tesla-pp-cli vehicles get-data-vehicle-config — Vehicle config (model, options, trim)tesla-pp-cli vehicles get-data-vehicle-state — Vehicle state (locks, software, sentry) subsettesla-pp-cli vehicles get-mobile-enabled — Is mobile control enabled in the cartesla-pp-cli vehicles get-nearby-chargers — Nearby Supercharger sites with stall availability subfieldtesla-pp-cli vehicles get-release-notes — Release notes for the current/queued software updatetesla-pp-cli vehicles get-service-data — Open service appointments and recent service history for this vehicletesla-pp-cli vehicles get-vehicle-data — Full vehicle state snapshot: charge, climate, drive, GUI, vehicle config, and softwareWhen you know what you want to do but not which command does it, ask the CLI directly:
tesla-pp-cli which "<capability in your own words>"which resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code 0 means at least one match; exit code 2 means no confident match — fall back to --help or use a narrower query.
tesla snap --all --json && tesla ready 5YJ3E1EA6XXXXXXXX --jsonCapture vehicle state for every car on the account, then check whether your primary vehicle is ready to drive.
tesla ready 5YJ3E1EA6XXXXXXXX --json --select ready,blockersOne JSON object: is the car ready to drive, and if not, why not. Use --select to limit response size for agents.
tesla cost ledger --since 30d --group supercharger,home --json --select total_usd,sessions,kwh_added,supercharger_ratioPer-month breakdown with dotted-path --select so the agent sees only the rollup fields, not every session.
tesla vehicles create-auto-conditioning-start 5YJ3E1EA6XXXXXXXX --jsonStart climate preconditioning. Run tesla ready <vin> ten minutes later to confirm cabin warmed up.
tesla supercharger watch 1000 --free-stalls 2 --watch --jsonSubscribe to free-stall transitions at a saved site; emits one JSON line per transition. Pipe to an agent for alerting.
tesla-pp-cli analytics --select battery_level,captured_at --limit 30 --jsonPull the 30 most recent vehicle-state rows from the local SQLite for trend analysis; same data TeslaMate would surface in Grafana.
# 1. Install tesla-control (clone+build, not go install @latest)
git clone https://github.com/teslamotors/vehicle-command.git
cd vehicle-command && go build -o tesla-control ./cmd/tesla-control
mv tesla-control ~/go/bin/ && cd ..
# 2. Generate keypair and scaffold public-key host
tesla-pp-cli auth fleet-template --gen-key --dest ./tesla-keys-host
cd tesla-keys-host && vercel deploy --prod
# 3. Register at developer.tesla.com with the Vercel hostname, copy client_id and client_secret
# 4. Register with Tesla (key-file auto-detected from ~/.tesla/)
tesla-pp-cli auth fleet-register \
--public-key-domain <your-host>.vercel.app \
--client-id <id> \
--client-secret-file <secret-file>
# 5. User OAuth login
tesla-pp-cli auth fleet-login
# 6. ONE-TIME: Enroll virtual key at the car (BLE+NFC required, must be at car)
tesla-control -ble -vin <VIN> add-key-request owner cloud_key
# Tap NFC card or phone key when the car prompts
# 7. Now remote commands work from anywhere
tesla-pp-cli command climate_on --vehicle <name> --send
tesla-pp-cli command unlock --vehicle <name> --sendAfter the one-time BLE+NFC pairing at the car, all signed commands work from anywhere with internet. Per-call cost: $0.001 plus a $0.02 wake if the car is asleep. Inside the $10/mo personal-use credit, that lands at roughly $0 net.
The --via flag overrides the default transport:
tesla-pp-cli command set_charge_limit --vehicle <name> --send -- percent=80
tesla-pp-cli command unlock --vehicle <name> --send --via fleet
tesla-pp-cli command flash_lights --vehicle <name> --send --via ble
tesla-pp-cli command honk_horn --vehicle <name> --send --via hermesDefaults: pre-2021 vehicles use REST, post-2021 vehicles use Fleet when enrolled. Use --via=hermes to force the Hermes relay path (free, but only for infotainment commands — charge, climate, honk, media). Use --via=ble for local Bluetooth commands.
# On laptop:
tesla auth export --out tesla-bundle.enc
scp tesla-bundle.enc user@mac-mini:~/
# On Mac mini:
tesla auth import ~/tesla-bundle.enc
tesla-pp-cli command honk_horn --vehicle <name> --send --via fleetExport creates an Argon2id plus AES-256-GCM bundle of the REST bearer, the Fleet bearer, and the enrolled ECDSA keypair. Copy it over Tailscale or any secure channel. Import on the remote, enter the passphrase, and the same Fleet creds plus the same enrolled key work from the new host. The car does not need to re-enroll; key identity rides on the keypair.
Text form (rendered consistently across SKILL.md viewers):
Is the vehicle pre-2021?
Yes -> REST (default path, no extra setup)
No -> Continue.
Is Fleet API enrolled?
Yes -> Fleet API (default for all signed commands, roughly $0/mo within personal-use credit)
No -> Continue.
Is the car within Bluetooth range of this host?
Yes -> BLE (free, all commands, no internet needed)
No -> Continue.
Is Hermes relay running and only need infotainment commands?
Yes -> Hermes (free, but only charge/climate/honk/media — no unlock/lock/trunk)
No -> Set up Fleet API (see Auth Setup below)
Deploying to a second host (cloud Mac mini, Pi)?
Use Fleet + `tesla auth export` and `tesla auth import` on the remote.The CLI requires tesla_auth for OAuth login. Install it first:
cargo install tesla_auth
# or on macOS: brew install adriankumpf/tap/tesla_authtesla-pp-cli auth loginThis subprocesses into tesla_auth, which opens Tesla's OAuth page in a native window. Log in there (Tesla owns MFA, captcha, SMS codes - we never see them), and tesla_auth captures the tokens. The CLI stores them in ~/.config/tesla-pp-cli/config.toml (mode 0600). Bearer tokens last 8h; the CLI silently re-mints them on 401 using the long-lived refresh token.
Headless/CI fallbacks when you already have a refresh token:
auth login --paste — reads a refresh token from stdinauth login --refresh-token <tok> — supplies the token as a flag2021+ Teslas require signed commands via the Fleet API. This is a one-time setup:
Install tesla-control (clone and build — go install @latest fails due to upstream replace directives):
git clone https://github.com/teslamotors/vehicle-command.git
cd vehicle-command
go build -o tesla-control ./cmd/tesla-control
mv tesla-control ~/go/bin/ # or somewhere on your $PATHScaffold public-key host and generate keypair:
tesla-pp-cli auth fleet-template --gen-key --dest ./tesla-keys-host
cd tesla-keys-host && vercel deploy --prodRegister at developer.tesla.com: Create an app with allowed origin/redirect pointing to your deployed host and http://localhost:8585/callback. Copy the client_id and client_secret.
Register with Tesla (the --key-file is auto-detected from ~/.tesla/):
tesla-pp-cli auth fleet-register \
--client-id <id> \
--client-secret-file <secret-path> \
--public-key-domain <your-host>.vercel.appComplete user OAuth:
tesla-pp-cli auth fleet-loginEnroll virtual key at the car (BLE+NFC required — the car must be nearby):
tesla-control -ble -vin <VIN> add-key-request owner cloud_key
# Tap your NFC card or phone key when the car promptsThis step cannot be done remotely — you must be at the car with Bluetooth and an NFC credential.
Run tesla-pp-cli doctor to verify setup.
Add --agent to any command. Expands to: --json --compact --no-input --no-color --yes.
Pipeable — JSON on stdout, errors on stderr
Filterable — --select keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs:
tesla-pp-cli charging --agent --select id,name,statusPreviewable — --dry-run shows the request without sending
Offline-friendly — sync/search commands can use the local SQLite store when available
Non-interactive — never prompts, every input is a flag
Explicit retries — use --idempotent only when an already-existing create should count as success
Commands that read from the local store or the API wrap output in a provenance envelope:
{
"meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."},
"results": <data>
}Parse .results for data and .meta.source to know whether it's live or local. A human-readable N results (live) summary is printed to stderr only when stdout is a terminal AND no machine-format flag (--json, --csv, --compact, --quiet, --plain, --select) is set — piped/agent consumers and explicit-format runs get pure JSON on stdout.
When you (or the agent) notice something off about this CLI, record it:
tesla-pp-cli feedback "the --since flag is inclusive but docs say exclusive"
tesla-pp-cli feedback --stdin < notes.txt
tesla-pp-cli feedback list --json --limit 10Entries are stored locally at ~/.tesla-pp-cli/feedback.jsonl. They are never POSTed unless TESLA_FEEDBACK_ENDPOINT is set AND either --send is passed or TESLA_FEEDBACK_AUTO_SEND=true. Default behavior is local-only.
Write what surprised you, not a bug report. Short, specific, one line: that is the part that compounds.
Every command accepts --deliver <sink>. The output goes to the named sink in addition to (or instead of) stdout, so agents can route command results without hand-piping. Three sinks are supported:
| Sink | Effect |
|---|---|
stdout | Default; write to stdout only |
file:<path> | Atomically write output to <path> (tmp + rename) |
webhook:<url> | POST the output body to the URL (application/json or application/x-ndjson when --compact) |
Unknown schemes are refused with a structured error naming the supported set. Webhook failures return non-zero and log the URL + HTTP status on stderr.
A profile is a saved set of flag values, reused across invocations. Use it when a scheduled agent calls the same command every run with the same configuration - HeyGen's "Beacon" pattern.
tesla-pp-cli profile save briefing --json
tesla-pp-cli --profile briefing charging
tesla-pp-cli profile list --json
tesla-pp-cli profile show briefing
tesla-pp-cli profile delete briefing --yesExplicit flags always win over profile values; profile values win over defaults. agent-context lists all available profiles under available_profiles so introspecting agents discover them at runtime.
| Code | Meaning |
|---|---|
| 0 | Success |
| 2 | Usage error (wrong arguments) |
| 3 | Resource not found |
| 4 | Authentication required |
| 5 | API error (upstream issue) |
| 7 | Rate limited (wait and retry) |
| 10 | Config error |
Parse $ARGUMENTS:
help, or --help → show tesla-pp-cli --help outputinstall → ends with mcp → MCP installation; otherwise → see Prerequisites above--agent)Install the MCP binary from this CLI's published public-library entry or pre-built release, then register it:
claude mcp add tesla-pp-mcp -- tesla-pp-mcpVerify: claude mcp list
which tesla-pp-cli
If not found, offer to install (see Prerequisites at the top of this skill).--agent flag:tesla-pp-cli <command> [subcommand] [args] --agenttesla-pp-cli <command> --help.© mvanhorn, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in cli-skills/pp-tesla of mvanhorn/printing-press-library.
Open the folder on GitHubat commit 76de244
Pp Tesla next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Pp Tesla this skillmvanhorn/printing-press-library | 2.1k | — | ~6.6k | Automated safety check: Notes | Apache-2.0 | |
| Cost Trackingaffaan-m/ECC | 276k | 1 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Cost Conversationruvnet/ruflo | 74k | — | ~407 | Automated safety check: Notes | MIT | |
| Cost Reportruvnet/ruflo | 74k | — | ~830 | Automated safety check: Notes | MIT | |
| Cost Optimizeruvnet/ruflo | 74k | — | ~997 | Automated safety check: Notes | MIT | |
| Cost Trackruvnet/ruflo | 74k | — | ~773 | Automated safety check: Notes | MIT |
affaan-m/ECC
Track and report Claude Code token usage, spending, and budgets from the local ECC cost-tracker metrics log.
ruvnet/ruflo
Per-conversation cost view — list every session in cost-tracking with started-at, message count, top model, and total cost
ruvnet/ruflo
Generate a cost report showing token usage and USD costs by agent and model
ruvnet/ruflo
Analyze token usage patterns and recommend cost optimizations with estimated savings
ruvnet/ruflo
Auto-capture per-session token usage from the Claude Code session jsonl and persist to the cost-tracking namespace
ruvnet/ruflo
Export cost-tracking telemetry in Prometheus textfile or webhook JSON formats — for external observability (Grafana, Datadog, custom dashboards)
mvanhorn/printing-press-library
Desktop automation through the real Rust agent-desktop CLI, published in Printing Press through a small bridge.
mvanhorn/printing-press-library
Search, browse, and download Google Fonts from the terminal via the gfonts CLI.
mvanhorn/printing-press-library
The free, offline Trigger phrases: search 1688 for, find a factory on 1688 for, wholesale price on 1688 for, who is the cheapest supplier on 1688 for, compare 1688 suppliers for, use 1688, run 1688.
mvanhorn/printing-press-library
Inspect known Activity Japan plan IDs or URLs, compare dated prices and sessions, check language-sitemap coverage, and hand off to canonical booking pages.
mvanhorn/printing-press-library
Every Admin By Request portal action, plus a local SQLite mirror of audit, events, inventory and requests for ad-hoc...
mvanhorn/printing-press-library
macOS screen capture, window recording, GIF conversion, and agent evidence bundles from the terminal.
Every Tesla mobile-app feature, plus a charging-cost ledger and supercharger queue watcher no other Tesla CLI ships. Pp Tesla is an agent skill from mvanhorn/printing-press-library. Every Tesla mobile-app feature, plus a charging-cost ledger and supercharger queue watcher no other Tesla CLI ships.
Pp Tesla fits situations like: phrases: is my tesla ready; precondition my tesla; how much did i spend on charging this month; supercharger queue at.
Run `npx skills add mvanhorn/printing-press-library --skill pp-tesla -a claude-code`. Or copy the skill folder (cli-skills/pp-tesla in mvanhorn/printing-press-library) into .claude/skills/pp-tesla in your project. Claude Code loads it when a task matches its description.
Run `npx skills add mvanhorn/printing-press-library --skill pp-tesla -a codex`. Or copy the skill folder (cli-skills/pp-tesla in mvanhorn/printing-press-library) into .agents/skills/pp-tesla in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mvanhorn/printing-press-library --skill pp-tesla -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pp-tesla, .gemini/skills/pp-tesla, .github/skills/pp-tesla and .opencode/skills/pp-tesla in your project.
Going by SKILL.md and its folder, Pp Tesla needs the command-line tools its instructions call (go, git, vercel, claude, npx and scp). Our summary lists: Node.js; Docker. Its frontmatter pre-approves these tools: Read, Bash.
SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Pp Tesla is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 6.6k tokens (SKILL.md is roughly 26k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Pp Tesla: Cost Tracking (affaan-m/ECC, 276k stars), Cost Conversation (ruvnet/ruflo, 74k stars), Cost Report (ruvnet/ruflo, 74k stars) and Cost Optimize (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
mvanhorn (a GitHub user) maintains it in mvanhorn/printing-press-library, which has 2,056 GitHub stars. The repository holds 506 skills in this directory. The repository was last updated on October 9, 2026.
Source: mvanhorn/printing-press-library on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.